Technology in Cancer Research & Treatment,
Год журнала:
2024,
Номер
23
Опубликована: Янв. 1, 2024
Clear
cell
renal
carcinoma
(ccRCC)
is
a
highly
lethal
urinary
malignancy
with
poor
overall
survival
(OS)
rates.
Integrating
computer
vision
and
machine
learning
in
pathomics
analysis
offers
potential
for
enhancing
classification,
prognosis,
treatment
strategies
ccRCC.
This
study
aims
to
create
model
predict
OS
ccRCC
patients.
In
this
study,
data
from
patients
the
TCGA
database
were
used
as
training
set,
clinical
serving
validation
set.
Pathological
features
extracted
H&E-stained
slides
using
PyRadiomics,
was
constructed
non-negative
matrix
factorization
(NMF)
algorithm.
The
model's
predictive
performance
assessed
through
Kaplan-Meier
(KM)
curves
Cox
regression
analysis.
Additionally,
differential
gene
expression,
ontology
(GO)
enrichment
analysis,
immune
infiltration,
mutational
conducted
investigate
underlying
biological
mechanisms.
A
total
of
368
patients,
comprising
two
subtypes
(Cluster
1
Cluster
2)
successfully
NMF
KM
revealed
that
2
associated
worse
OS.
76
genes
identified
between
subtypes,
primarily
involving
extracellular
organization
structure.
Immune-related
genes,
including
CTLA4,
CD80,
TIGIT,
expressed
2,
while
VHL
PBRM1
along
mutations
PI3K-Akt,
HIF-1,
MAPK
signaling
pathways,
exhibited
mutation
rates
exceeding
40%
both
subtypes.
learning-based
effectively
predicts
differentiates
critical
roles
immune-related
CTLA4
pathways
offer
new
insights
further
research
on
molecular
mechanisms,
diagnosis,
Bone
metastases
(BM)
represent
a
prevalent
complication
of
tumors.
Early
and
accurate
diagnosis,
however,
is
significant
hurdle
for
radiologists.
Recently,
artificial
intelligence
(AI)
has
emerged
as
valuable
tool
to
assist
radiologists
in
the
detection
BM.
This
meta-analysis
was
undertaken
evaluate
AI
diagnostic
accuracy
Two
reviewers
performed
an
exhaustive
search
several
databases,
including
Wei
Pu
(VIP)
database,
China
National
Knowledge
Infrastructure
(CNKI),
Web
Science,
Cochrane
Library,
Ovid-Embase,
Ovid-Medline,
Wan
Fang
Biology
Medicine
(CBM),
from
their
inception
December
2024.
focused
on
studies
that
developed
and/or
validated
techniques
detecting
BM
magnetic
resonance
imaging
(MRI)
or
computed
tomography
(CT).
A
hierarchical
model
used
calculate
odds
ratio
(DOR),
negative
likelihood
(NLR),
positive
(PLR),
area
under
curve
(AUC),
specificity
(SP),
pooled
sensitivity
(SE).
The
risk
bias
applicability
were
assessed
using
Prediction
Model
Risk
Bias
Assessment
Tool
(PROBAST),
while
Transparent
Reporting
multivariable
prediction
individual
prognosis
diagnosis-artificial
(TRIPOD-AI)
employed
evaluating
quality
evidence.
review
covered
20
articles,
among
them,
16
included
meta-analysis.
results
revealed
SE
0.88
(0.82–0.92),
SP
0.89
(0.84–0.93),
AUC
0.95
(0.92–0.96),
PLR
8.1
(5.57–11.80),
NLR
0.14
(0.09–0.21)
DOR
58
(31–109).
When
focusing
algorithms.
Based
ML,
(0.77–0.92),
0.93
(0.91–0.95).
DL,
(0.81–0.95),
(0.81–0.94),
(0.93–0.97).
underscores
substantial
value
identifying
Nevertheless,
in-depth
large-scale
prospective
research
should
be
carried
out
confirming
AI's
clinical
utility
management.
Frontiers in Oncology,
Год журнала:
2025,
Номер
14
Опубликована: Янв. 10, 2025
The
prediction
of
survival
outcomes
is
a
key
factor
in
making
decisions
for
prostate
cancer
(PCa)
treatment.
Advances
computer-based
technologies
have
increased
the
role
machine
learning
(ML)
methods
predicting
prognosis.
Due
to
various
effective
treatments
available
each
non-linear
landscape
PCa,
integration
ML
can
help
offer
tailored
treatment
strategies
and
precision
medicine
approaches,
thus
improving
patients
with
PCa.
There
has
been
an
upsurge
studies
utilizing
predict
these
using
complex
datasets,
including
patient
tumor
features,
radiographic
data,
population-based
databases.
This
review
aims
explore
evolving
associated
Specifically,
we
will
focus
on
applications
forecasting
biochemical
recurrence-free,
progression
castration-resistance-free,
metastasis-free,
overall
survivals.
Additionally,
suggest
areas
need
further
research
future
enhance
utility
more
clinically-utilizable
PCa
prognosis
optimization.
Frontiers in Cardiovascular Medicine,
Год журнала:
2025,
Номер
11
Опубликована: Янв. 13, 2025
Objectives
To
evaluate
the
feasibility
of
utilizing
cardiac
computer
tomography
(CT)
images
for
extracting
radiomic
features
myocardium
at
junction
between
left
atrial
appendage
(LAA)
and
atrium
(LA)
in
patients
with
fibrillation
(AF)
to
its
asscociation
risk
AF.
Methods
A
retrospective
analysis
was
conducted
on
82
cases
AF
56
control
group
who
underwent
CT
our
hospital
from
May
2022
2023,
recorded
clinical
information.
The
morphological
parameters
LAA
were
measured.
radiomics
model,
a
clincal
feature
model
combining
constructed.
built
by
myocardial
tissue
using
Pyradiomics,
employing
Least
absolute
shrinkage
selection
operator
(LASSO)
method
selection,
random
forest
support
vector
machine
(SVM)
classifier.
Results
There
[44
males,
65.00
(59,
70)],
(21
61.09
±
7.18).
Age,
BMI,
hypertension,
CHA2DS-VASC
score,
neutrophil
lymphocyte
ratio
(NLR),
volume,
LA
thickness
LA,
area,
circumference,
short
diameter,
long
diameter
opening,
significantly
different
(
P
<
0.05).
After
conducting
multivariate
logistic
regression
analysis,
it
found
that
NLR
score
related
12
extracted
identified.
ROC
curve
confirmed
nomogram
based
scores
factors
can
effectively
predict
(AUC
0.869).
Conclusion
Radiomics
enables
extraction
characteristics
which
are
AF,
facilitating
assessment
relationship
combination
enhances
evaluation
capabilities
significantly.
ORTHOPAEDICS TRAUMATOLOGY and PROSTHETICS,
Год журнала:
2024,
Номер
1, С. 53 - 58
Опубликована: Апрель 14, 2024
Prostate
cancer
is
the
second
most
common
cause
of
malignancy
in
men,
with
bone
metastases
being
a
significant
source
morbidity
and
mortality
advanced
cases.
Objective.
To
give
clinical
example
patient
pathological
transtrochanteric
fracture
right
femur
displacement
fragments,
presence
metastasis
at
site,
to
emphasize
importance
3D-training
before
surgery.
Methods.
A
impairment
function
lower
extremity
against
background
pain
syndrome
given.
The
diagnosis
was
established:
site.
Pre-surgical
training
carried
out
using
3D-model
total
endoprosthetics
hip
joint
revision
individual
implant
cement
fixation
type
out.
fully
recovered
limb
joint,
eliminated,
sleep
normalized.
use
for
preoperative
surgeons
made
it
possible
rationally
limit
traumatization
healthy
tissues
during
tumor
removal,
prevent
complications
optimize
time
surgical
intervention
thus
minimize
blood
loss.
Conclusions.
surgery
followed
by
prosthetics
special
oncological
endoprosthesis
provided
satisfactory
functional
results
restoration
patient's
quality
life
given
case.
key
careful
preparation
intervention,
taking
into
account
anatomical
features
process
adjacent
tissues,
which
allows
you
significantly
terms
operation
reduce
loss,
also
provides
valuable
experience
further
practice.
2022 IEEE International Conference on Automation, Quality and Testing, Robotics (AQTR),
Год журнала:
2024,
Номер
4, С. 1 - 6
Опубликована: Май 16, 2024
Medical
imaging
is
a
very
useful
tool
in
healthcare,
various
technologies
being
employed
to
non-invasively
peek
inside
the
human
body.
Deep
learning
with
neural
networks
radiology
was
welcome
–
albeit
cautiously
by
radiologist
community.
Most
of
currently
deployed
or
researched
deep
solutions
are
applied
on
already
generated
images
medical
scans,
use
aid
generation
such
images,
them
for
identifying
specific
substance
markers
spectrographs.
This
paper's
author
posits
that
if
were
trained
directly
raw
signals
from
scanning
machines,
they
would
gain
access
more
nuanced
information
than
processed
hence
training
and
later,
inferences
become
accurate.
The
paper
presents
main
current
applications
radiography,
ultrasonography,
electrophysiology,
discusses
whether
proposed
network
feasible.
